diff --git a/src/datatrove/pipeline/readers/base.py b/src/datatrove/pipeline/readers/base.py
index e7f4569..487cad5 100644
--- a/src/datatrove/pipeline/readers/base.py
+++ b/src/datatrove/pipeline/readers/base.py
@@ -62,7 +62,7 @@ class BaseReader(PipelineStep):
             "text": data.pop(self.text_key, ""),
             "id": data.pop(self.id_key, f"{path}/{id_in_file}"),
             "media": data.pop("media", []),
-            "metadata": data.pop("metadata", {}) | data,  # remaining data goes into metadata
+            # "metadata": data.pop("metadata", {}) | data,  # remaining data goes into metadata
         }
 
     def get_document_from_dict(self, data: dict, source_file: str, id_in_file: int | str):
diff --git a/src/datatrove/pipeline/tokens/tokenizer.py b/src/datatrove/pipeline/tokens/tokenizer.py
index d6040a0..e86f9bb 100644
--- a/src/datatrove/pipeline/tokens/tokenizer.py
+++ b/src/datatrove/pipeline/tokens/tokenizer.py
@@ -358,7 +358,7 @@ class DocumentTokenizer(PipelineStepWithTokenizer):
         # tokenize document's text in batches to go faster – we compute loss values independently if needed
         for batch in batched(data, self.batch_size):
             with self.track_time(unit="batch"):
-                encoded_batch: list[Encoding] = self.tokenizer.encode_batch([document.text for document in batch])
+                encoded_batch: list[Encoding] = self.tokenizer.encode_batch([document.text[0] for document in batch])
                 for document, encoded in zip(batch, encoded_batch):
                     tokens = encoded.ids
                     loss_values = self.get_loss_values(document, encoded)
diff --git a/src/datatrove/utils/tokenization.py b/src/datatrove/utils/tokenization.py
index 5ce298f..3ff067c 100644
--- a/src/datatrove/utils/tokenization.py
+++ b/src/datatrove/utils/tokenization.py
@@ -48,12 +48,13 @@ class PipelineStepWithTokenizer(PipelineStep, ABC):
             if not self.tokenizer_name_or_path:
                 raise ValueError("self.tokenizer_name_or_path needs to be set!")
             self._tokenizer = load_tokenizer(self.tokenizer_name_or_path)
-            if self._post_processor:
-                self._tokenizer.post_processor = self._post_processor
-            elif self.eos_token:
-                self._tokenizer.post_processor = TemplateProcessing(
-                    single="$A <EOS>",
-                    special_tokens=[("<EOS>", self.tokenizer.token_to_id(self.eos_token))],
-                    pair=None,
-                )
+            self.eos_token = self._tokenizer.token_to_id(self.eos_token)
+            # if self._post_processor:
+            #     self._tokenizer.post_processor = self._post_processor
+            # elif self.eos_token:
+            #     self._tokenizer.post_processor = TemplateProcessing(
+            #         single="$A <EOS>",
+            #         special_tokens=[("<EOS>", self.tokenizer.token_to_id(self.eos_token))],
+            #         pair=None,
+            #     )
         return self._tokenizer